© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-RES-MATRYOSHKA-DC
    7. 2704
    Prev
    Next
    INDEX
    Explanations

    references to outside works in academic papers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.55
     Reverso
    -0.53
     viewType
    -0.53
     fan
    -0.49
    خت
    -0.48
    Rohy
    -0.48
     IconData
    -0.46
    XMLSchema
    -0.45
    InstanceOf
    -0.44
    OfMonth
    -0.44
    POSITIVE LOGITS
     fubject
    0.67
     Mahomet
    0.66
     ſeveral
    0.64
     Theſe
    0.63
     intptr
    0.63
     Chriftian
    0.60
    šinou
    0.60
     Vikipedi
    0.60
     Cæsar
    0.60
     ostavi
    0.59
    Activations Density 0.729%

    No Known Activations